Morreale, LucaAigerman, NoamKim, Vladimir G.Mitra, Niloy J.Bermano, Amit H.Kalogerakis, Evangelos2024-04-302024-04-3020241467-8659https://doi.org/10.1111/cgf.15005https://diglib7.eg.org/handle/10.1111/cgf15005We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Lack of annotated data prohibits direct inference of 3D semantic priors; instead, current state-of-the-art methods predominantly optimize geometric properties or require varying amounts of manual annotation. To overcome the lack of annotated training data, we distill semantic matches from pre-trained vision models: our method renders the pair of untextured 3D shapes from multiple viewpoints; the resulting renders are then fed into an off-the-shelf imagematching strategy that leverages a pre-trained visual model to produce feature points. This yields semantic correspondences, which are projected back to the 3D shapes, producing a raw matching that is inaccurate and inconsistent across different viewpoints. These correspondences are refined and distilled into an inter-surface map by a dedicated optimization scheme, which promotes bijectivity and continuity of the output map. We illustrate that our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement. Furthermore, it proves effective in scenarios with high semantic complexity, where objects are non-isometrically related, as well as in situations where they are nearly isometric.CCS Concepts: Computing methodologies -> Shape analysis; Mesh geometry models; Feature selectionComputing methodologiesShape analysisMesh geometry modelsFeature selection10.1111/cgf.1500513 pages